bert_uncased_fake_news

This model is a fine-tuned version of distilbert-base-uncased on the kaggle fake news detection english dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.0015
• Train Accuracy: 0.9997
• Validation Loss: 0.0048
• Validation Accuracy: 0.9983
• Test F1 Score (macro): 0.9989

How to use

You can use this model directly with a pipeline for text classification:

>>> from transformers import pipeline
>>> classifier = pipeline("text-classification", model="rasyosef/bert_uncased_fake_news")
>>> classifier(["Wow! Talk about clueless! Austen Fletcher approaches anti-Trump protesters and gets clueless answers on why they re against Trump:Thought you might enjoy this  @PrisonPlanet @allidoisowen @JackPosobiec pic.twitter.com/kdYm2WlfdB  austen fletcher (@fleccas) July 17, 2017"])

[{'label': 'Fake News', 'score': 0.9999557733535767}]

Model description

More information needed

Intended uses & limitations

More information needed

Training hyperparameters

The following hyperparameters were used during training:

• optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 2814, 'end_learning_rate': 0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
• training_precision: float32

Training results

Framework versions

• Transformers 4.35.2
• TensorFlow 2.15.0
• Datasets 2.16.1
• Tokenizers 0.15.0